菜单
Use when the user says "syscheck" or asks for a parallel system health check. Fans out THREE subagents via the `task` tool — one checks CPU, one network, one memory — using only safe read-only commands, then synthesizes their results into one report. Demonstrates parallel subagent fan-out in opencode.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
Use when the user says "netwatch" or asks to measure network stats (ping latency, packet loss, interface throughput) in the background. Launches a background subagent via the `task` tool that runs ~20s of measurements, then returns control immediately so the user can keep talking. Demonstrates background subagent invocation in opencode.
Private sieve subskill. Invoked by the sieve controller after each pass; not user-invocable. Reads sieve.state and draws the current grid — remaining primes vs. struck (composite) numbers.
Demonstrates cyclic skill invocation — runs the Sieve of Eratosthenes by invoking a private "strike" subskill once per prime, re-rendering a visual grid after each pass. Takes an upper limit n. Use to show one skill invoking another skill N times in a loop.
Private sieve subskill. Invoked by the sieve controller once per prime; not user-invocable. Strikes the multiples of a single prime p out of the sieve and records them in sieve.state.
Use when the user says "syscheck" or asks for a parallel system health check. Fans out THREE subagents at once via the Agent tool — one checks CPU, one network, one memory — using only safe read-only commands, then synthesizes their results into one report. Demonstrates parallel subagent fan-out in Claude Code.
Demonstrates recursive self-invocation with a depth limit. Performs a breadth-first (level-order) traversal of the decision tree in tree.json by invoking ITSELF once per level — each call expands the current frontier and recurses on the next, stopping at a maximum depth. Takes an optional max depth.
| name | syscheck |
| description | Use when the user says "syscheck" or asks for a parallel system health check. Fans out THREE subagents via the `task` tool — one checks CPU, one network, one memory — using only safe read-only commands, then synthesizes their results into one report. Demonstrates parallel subagent fan-out in opencode. |
Demonstrates fanning out work to several subagents at once with opencode's
task tool. Instead of one agent checking CPU, network, and memory one after
another, the main agent invokes three subagents in parallel — each owns one
subsystem — and then combines their findings into a single system-health report.
Each task call spawns a subagent in its own context that runs
asynchronously: the call returns control to the main agent immediately, and
opencode notifies the main agent when the subagent completes. To run the
three checks concurrently, issue all three task calls in one message;
opencode starts them together, and you gather and synthesize their results as
they report back.
This extends the background-subagent pattern (one subagent) to fan-out:
several independent subagents at once, each in its own context, with the main
agent acting as orchestrator.
Safety: every subagent uses read-only commands only — it observes the system and never modifies it. No writes to files,
sysctl, services, or config.
Invoke three subagents in a single message (so they start concurrently)
with the task tool, subagent_type: "general". Hand each one of the three
task prompts below. Do not run the checks yourself, and do not chain
any tool call after them in the same message that depends on their results —
let the turn end so control returns to the user while the subagents run.
① CPU — description: "check cpu":
Check CPU status using only safe, read-only commands (no writes, no config or sysctl changes). Run:
lscpu(model, core count),nproc,uptime(load average), andtop -bn1 | head -n 15for current utilization. Report a short summary: CPU model, physical/logical cores, load average (1/5/15 min), and approximate CPU utilization. Return only the summary.
② Network — description: "check network":
Check network status using only safe, read-only commands (no writes, no config changes). Find the primary interface with
ip route get 1.1.1.1. Runip -s link show <iface>(counters),ip addr show <iface>(address), andping -c 5 -W 2 1.1.1.1for latency/loss (fall back to8.8.8.8). Report: interface, IP, gateway, RTT min/avg/max (ms), packet loss %. Return only the summary.
③ Memory — description: "check memory":
Check memory status using only safe, read-only commands (no writes). Run:
free -h(RAM + swap) andvmstat -s -S Mfor detail. Report: total RAM, used, available, used %, and swap used/total. Return only the summary.
Immediately tell the user, in one or two lines, that three checks (CPU, network, memory) are now running in parallel in the background and they can keep talking meanwhile. Then end your turn — do not block waiting for the subagents.
When the subagents complete, you will be notified with their results (one notification per subagent). Once all three have reported, synthesize their summaries into one short system-health report — a section or row per subsystem — and flag anything notable (high load, packet loss, low available memory).
Three things make this background fan-out, not blocking calls:
lscpu/ping/free output never enters the main transcript — only the
three short summaries come back.The teaching point: fan-out. Three independent subagents work in parallel, each in its own context, and the main agent only collects and combines the distilled results — fire-and-continue, not fire-and-wait.